© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116848
    Prev
    Next
    INDEX
    Explanations

    I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.20
     someday
    -0.16
     ultimately
    -0.16
     eventual
    -0.15
     initially
    -0.15
     soon
    -0.15
     Eventually
    -0.14
    Eventually
    -0.13
     presently
    -0.13
     subsequently
    -0.13
    POSITIVE LOGITS
     realized
    0.11
     realize
    0.10
     irrelevant
    0.10
     already
    0.09
     realizes
    0.09
     purely
    0.09
     realization
    0.09
    å·²
    0.09
    anse
    0.08
     either
    0.08
    Activations Density 0.055%

    No Known Activations